{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:P3XNBJUCZQNLLHO4FNIQSZ2RJP","merge_version":"pith-open-graph-merge-v1","event_count":2,"valid_event_count":2,"invalid_event_count":0,"equivocation_count":0,"current":{"canonical_record":{"metadata":{"abstract_canon_sha256":"ea62864f4d92e42f412ddebdfb6543ee07e6c598660ea5af84980391a7f83952","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2025-02-18T05:54:56Z","title_canon_sha256":"dcaadfa4ca1419efc106c82b2fb19865e823244504f0f39d72115d574fba52f6"},"schema_version":"1.0","source":{"id":"2502.12560","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2502.12560","created_at":"2026-07-05T10:17:54Z"},{"alias_kind":"arxiv_version","alias_value":"2502.12560v2","created_at":"2026-07-05T10:17:54Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2502.12560","created_at":"2026-07-05T10:17:54Z"},{"alias_kind":"pith_short_12","alias_value":"P3XNBJUCZQNL","created_at":"2026-07-05T10:17:54Z"},{"alias_kind":"pith_short_16","alias_value":"P3XNBJUCZQNLLHO4","created_at":"2026-07-05T10:17:54Z"},{"alias_kind":"pith_short_8","alias_value":"P3XNBJUC","created_at":"2026-07-05T10:17:54Z"}],"graph_snapshots":[{"event_id":"sha256:93d2ab5f6bebd0e65d022efcab00083cb88ded4da39a4cf2af16ffcc125e40c2","target":"graph","created_at":"2026-07-05T10:17:54Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"graph_snapshot":{"author_claims":{"count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","strong_count":0},"builder_version":"pith-number-builder-2026-05-17-v1","claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"integrity":{"available":true,"clean":true,"detectors_run":[],"endpoint":"/pith/2502.12560/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"The necessity of language-specific tokenizers intuitively appears crucial for effective natural language processing, yet empirical analyses on their significance and underlying reasons are lacking. This study explores how language-specific tokenizers influence the behavior of Large Language Models predominantly trained with English text data, through the case study of Korean. The research unfolds in two main stages: (1) the development of a Korean-specific extended tokenizer and (2) experiments to compare models with the basic tokenizer and the extended tokenizer through various Next Token Pre","authors_text":"Hyopil Shin, Jaeyoon Kim, Jean Seo, Sungjoo Byun","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2025-02-18T05:54:56Z","title":"How does a Language-Specific Tokenizer affect LLMs?"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2502.12560","kind":"arxiv","version":2},"verdict":{"created_at":null,"id":null,"model_set":{},"one_line_summary":"","pipeline_version":null,"pith_extraction_headline":"","strongest_claim":"","weakest_assumption":""}},"verdict_id":null}}],"author_attestations":[],"timestamp_anchors":[],"storage_attestations":[],"citation_signatures":[],"replication_records":[],"corrections":[],"mirror_hints":[],"record_created":{"event_id":"sha256:9a55b4662adf1cbc157466eb7ee9901123d8a00341aab0c52c8164fed06ee6d0","target":"record","created_at":"2026-07-05T10:17:54Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"attestation_state":"computed","canonical_record":{"metadata":{"abstract_canon_sha256":"ea62864f4d92e42f412ddebdfb6543ee07e6c598660ea5af84980391a7f83952","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2025-02-18T05:54:56Z","title_canon_sha256":"dcaadfa4ca1419efc106c82b2fb19865e823244504f0f39d72115d574fba52f6"},"schema_version":"1.0","source":{"id":"2502.12560","kind":"arxiv","version":2}},"canonical_sha256":"7eeed0a682cc1ab59ddc2b510967514bebb2bba07860d02c19b02ec6fd3bc347","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"7eeed0a682cc1ab59ddc2b510967514bebb2bba07860d02c19b02ec6fd3bc347","first_computed_at":"2026-07-05T10:17:54.587496Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T10:17:54.587496Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"ta+kIFZ1hCb4kYEwUWKC3pd7HenSMB6p+tR+p3GccNw0FLQqFzIAzSNoNd6zUEMVVSfxMDgrV2EtfNIKny4DBg==","signature_status":"signed_v1","signed_at":"2026-07-05T10:17:54.587977Z","signed_message":"canonical_sha256_bytes"},"source_id":"2502.12560","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:9a55b4662adf1cbc157466eb7ee9901123d8a00341aab0c52c8164fed06ee6d0","sha256:93d2ab5f6bebd0e65d022efcab00083cb88ded4da39a4cf2af16ffcc125e40c2"],"state_sha256":"2bbbc237fbf0af21fa1903d41f902493532dfeec2ed177efecadbe47778c79fc"}